US20160070658A1 - Multi-level, hardware-enforced domain separation using a separation kernel on a multicore processor with a shared cache - Google Patents
Multi-level, hardware-enforced domain separation using a separation kernel on a multicore processor with a shared cache Download PDFInfo
- Publication number
- US20160070658A1 US20160070658A1 US14/480,456 US201414480456A US2016070658A1 US 20160070658 A1 US20160070658 A1 US 20160070658A1 US 201414480456 A US201414480456 A US 201414480456A US 2016070658 A1 US2016070658 A1 US 2016070658A1
- Authority
- US
- United States
- Prior art keywords
- shared
- processing cores
- domains
- management units
- memory
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000926 separation method Methods 0.000 title claims abstract description 53
- 230000015654 memory Effects 0.000 claims abstract description 59
- 238000013507 mapping Methods 0.000 claims abstract description 21
- 230000003068 static effect Effects 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims description 52
- 238000000034 method Methods 0.000 claims description 22
- 230000002093 peripheral effect Effects 0.000 claims description 11
- 238000007726 management method Methods 0.000 claims 22
- 238000013500 data storage Methods 0.000 claims 11
- 230000008569 process Effects 0.000 description 10
- 239000004744 fabric Substances 0.000 description 9
- 238000002955 isolation Methods 0.000 description 8
- 230000008901 benefit Effects 0.000 description 6
- 238000000638 solvent extraction Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 230000014616 translation Effects 0.000 description 2
- 208000035155 Mitochondrial DNA-associated Leigh syndrome Diseases 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 239000000872 buffer Substances 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 238000003331 infrared imaging Methods 0.000 description 1
- 208000003531 maternally-inherited Leigh syndrome Diseases 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F12/00—Accessing, addressing or allocating within memory systems or architectures
- G06F12/14—Protection against unauthorised use of memory or access to memory
- G06F12/1458—Protection against unauthorised use of memory or access to memory by checking the subject access rights
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F12/00—Accessing, addressing or allocating within memory systems or architectures
- G06F12/02—Addressing or allocation; Relocation
- G06F12/08—Addressing or allocation; Relocation in hierarchically structured memory systems, e.g. virtual memory systems
- G06F12/0802—Addressing of a memory level in which the access to the desired data or data block requires associative addressing means, e.g. caches
- G06F12/0806—Multiuser, multiprocessor or multiprocessing cache systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F12/00—Accessing, addressing or allocating within memory systems or architectures
- G06F12/02—Addressing or allocation; Relocation
- G06F12/08—Addressing or allocation; Relocation in hierarchically structured memory systems, e.g. virtual memory systems
- G06F12/0802—Addressing of a memory level in which the access to the desired data or data block requires associative addressing means, e.g. caches
- G06F12/0806—Multiuser, multiprocessor or multiprocessing cache systems
- G06F12/084—Multiuser, multiprocessor or multiprocessing cache systems with a shared cache
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F12/00—Accessing, addressing or allocating within memory systems or architectures
- G06F12/02—Addressing or allocation; Relocation
- G06F12/08—Addressing or allocation; Relocation in hierarchically structured memory systems, e.g. virtual memory systems
- G06F12/0802—Addressing of a memory level in which the access to the desired data or data block requires associative addressing means, e.g. caches
- G06F12/0806—Multiuser, multiprocessor or multiprocessing cache systems
- G06F12/0842—Multiuser, multiprocessor or multiprocessing cache systems for multiprocessing or multitasking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F12/00—Accessing, addressing or allocating within memory systems or architectures
- G06F12/02—Addressing or allocation; Relocation
- G06F12/08—Addressing or allocation; Relocation in hierarchically structured memory systems, e.g. virtual memory systems
- G06F12/10—Address translation
- G06F12/1009—Address translation using page tables, e.g. page table structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F12/00—Accessing, addressing or allocating within memory systems or architectures
- G06F12/02—Addressing or allocation; Relocation
- G06F12/08—Addressing or allocation; Relocation in hierarchically structured memory systems, e.g. virtual memory systems
- G06F12/10—Address translation
- G06F12/1081—Address translation for peripheral access to main memory, e.g. direct memory access [DMA]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/062—Securing storage systems
- G06F3/0622—Securing storage systems in relation to access
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0662—Virtualisation aspects
- G06F3/0665—Virtualisation aspects at area level, e.g. provisioning of virtual or logical volumes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
- G06F3/0671—In-line storage system
- G06F3/0673—Single storage device
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/4401—Bootstrapping
- G06F9/4405—Initialisation of multiprocessor systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/468—Specific access rights for resources, e.g. using capability register
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/54—Interprogram communication
- G06F9/547—Remote procedure calls [RPC]; Web services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
- G06F2009/45587—Isolation or security of virtual machine instances
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
- G06F2009/45595—Network integration; Enabling network access in virtual machine instances
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2212/00—Indexing scheme relating to accessing, addressing or allocation within memory systems or architectures
- G06F2212/10—Providing a specific technical effect
- G06F2212/1052—Security improvement
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2212/00—Indexing scheme relating to accessing, addressing or allocation within memory systems or architectures
- G06F2212/28—Using a specific disk cache architecture
- G06F2212/281—Single cache
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2212/00—Indexing scheme relating to accessing, addressing or allocation within memory systems or architectures
- G06F2212/62—Details of cache specific to multiprocessor cache arrangements
Definitions
- the present disclosure is directed in general to multicore processor systems, and, more particularly, to multicore processor systems with at least one shared cache.
- Multicore processors include multiple processing cores on the same integrated circuit die, usually with private, high-level caches also on the same die and often with a shared, lower-level cache either on the same die or in the same package. These configurations have made possible previously theoretical but impractical security attacks, such as timed thread switching and page table entry modification.
- a separation kernel isolating memory domains within a shared system memory is executed on the cores of a multicore processor having hardware security enforcement for static virtual address mappings, to implement an efficient embedded multi-level security system.
- Shared caches are either disabled or constrained by the same static virtual address mappings using the hardware security enforcement available, to isolate domains accessible to select cores and reduce security risks from data co-mingling.
- FIG. 1 is a high level block diagram of a system implementing multi-level, hardware-enforced domain separation using a separation kernel on a multicore processor with a shared cache in accordance with embodiments of the present disclosure
- FIG. 2 is a high level block diagram of a multicore processor with a shared cache that may be employed to implement multi-level, hardware-enforced domain separation using a separation kernel in accordance with embodiments of the present disclosure
- FIG. 3 diagrammatically illustrates one core isolation and partitioning configuration of a multicore processor with a shared cache that may be realized with a separation kernel to implement a multi-level, hardware-enforced domain separation in accordance with embodiments of the present disclosure
- FIG. 4 diagrammatically illustrates another core isolation and partitioning configuration of a multicore processor with a shared cache that may be realized with a separation kernel to implement a multi-level, hardware-enforced domain separation in accordance with embodiments of the present disclosure
- FIGS. 5 and 6 are high level flowcharts for processes of configuring core isolation and partitioning in a multicore processor with a shared cache executing a separation kernel to implement a multi-level, hardware-enforced domain separation in accordance with embodiments of the present disclosure.
- MLS multi-level secure
- AMP symmetric multi-processing
- SoC Freescale QorIQ system-on-a-chip
- QorIQ Trust Architecture the built-in QorIQ Trust Architecture
- FIG. 1 is a high level block diagram of a system implementing multi-level, hardware-enforced domain separation using a separation kernel on a multicore processor with a shared cache in accordance with embodiments of the present disclosure.
- the system 100 includes a multicore processor 101 , which in the exemplary embodiment is one of the QorIQ family of multicore processors available from Freescale Semiconductor, Inc., such as the model P4080 processor.
- the multicore processor 101 is communicably coupled by a system bus 102 to a system memory 103 , and, in the exemplary embodiment, also to a transceiver 104 and to a plurality of peripheral devices 105 , 106 and 107 .
- the system may be implemented, for example, as part of an unmanned aerial vehicle (UAV), an infrared imaging satellite, or a missile system.
- UAV unmanned aerial vehicle
- UIR infrared imaging satellite
- missile system a missile system
- FIG. 2 is a high level block diagram of a multicore processor with a shared cache that may be employed to implement multi-level, hardware-enforced domain separation using a separation kernel in accordance with embodiments of the present disclosure.
- the multicore processor 101 is preferably a Freescale QorIQ processor, although any multiprocessor with the security features described herein may be employed instead.
- Multicore processor 101 includes a plurality of processors. In the exemplary embodiment, eight processors 201 a - 201 h, named “core 0” to “core 7,” are formed in the integrated circuit of multicore processor 101 .
- Each processor 201 a - 201 h includes a processing core 202 , the circuitry executing instructions of a program.
- Each processor also includes a level one (L1) data cache (“D-Cache”) 203 and an L1 instruction cache (“I-Cache”) 204 , each 32 kilobytes (KB) in size and each holding working copies of data and program instructions, respectively, for operations executed within the respective processor 202 .
- Each processor 202 also includes a level two (L2) backside cache 205 (e.g., 128 KB), a combined data and instruction cache.
- HV MMU memory management unit
- HV MMU hardware virtualization memory management unit
- the HV MMU 206 performs, in hardware, virtualization of memory addresses for locations within system memory. That is, ranges of virtual memory addresses defined for use by software operating within the processor 201 a (or 201 b, 201 c, etc.) map to physical memory locations.
- the mapping and subsequent address translations are controlled by HV MMU 206 , which is employed at least during read or write accesses to system memory and which operates cooperatively for cache control and, to the extent necessary, bus arbitration.
- the two L1 caches 203 and 204 are communicably coupled to a coherency fabric 207 , which in the example of a QorIQ processor is implemented by the CoreNet coherency fabric.
- Front side level three (L3) caches 208 and 209 (e.g., 1024 KB) are also communicably coupled to coherency fabric 207 , and are each coupled to a respective memory controller 210 and 211 .
- L3 caches 208 and 209 are shared by processors 201 a - 201 h, and thus each can contain data for software executing within different ones of those processors. While applications executing in the processors 201 a - 201 h may be designed to operate exclusively within respective memory address ranges, the co-mingling of data within a shared cache presents potential opportunities for security attacks.
- the coherency fabric 207 manages coherency of the caches 203 , 204 and 205 for each processor 201 a - 201 h and of shared caches 208 and 209 with each other and with system memory (not shown).
- the coherency fabric 207 also provides scalable on-chip, point-to-point connectivity supporting concurrent traffic to and from multiple resources connected to the fabric 207 , eliminating single-point bottlenecks for non-competing resources and thus avoiding various bus contention and latency issues associated with scaling shared bus/shared memory architectures.
- the coherency fabric 207 is connected with communications resources (not shown), such as Ethernet frame managers/buffers and input/output (I/O) ports according to various other communications standards with test/debug interfaces (also not shown), and/or with security engines and managers (also not shown).
- communications resources such as Ethernet frame managers/buffers and input/output (I/O) ports according to various other communications standards with test/debug interfaces (also not shown), and/or with security engines and managers (also not shown).
- PAMUs peripheral access management units
- the PAMUs 212 - 216 serve as the input/output (I/O) MMUs for the multicore processor 101 , providing I/O device-to-memory access control, protection and address translation in a manner allowing creation of a securely partitioned system.
- the multicore processor 101 may be configured so that all DMA-capable I/O devices must go through one of the PAMUs for memory accesses, with the respective PAMU employing a set of software-configured tables to determine what physical address ranges the device is permitted to access.
- DMA direct memory access
- FIG. 3 diagrammatically illustrates one core isolation and partitioning configuration of a multicore processor with a shared cache that may be realized with a separation kernel to implement a multi-level, hardware-enforced domain separation in accordance with embodiments of the present disclosure.
- the configuration 300 employs all processors 201 a - 201 h of the exemplary multi-core processor of FIG. 2 , together with the respective HV MMUs 206 a - 206 h and PAMUs 214 - 215 .
- each of the processors 201 a - 201 h executes a separation kernel and the L3 caches 208 - 209 are disabled (not utilized).
- a “separation kernel” is an operating system security kernel used to create an environment that is indistinguishable from physically distributed systems; that is, each domain appears to all other domains as a separate, isolated machine and information flow between domains is limited to known, external communication lines.
- the characteristics of a separation kernel are defined, for example, by the Separation Kernel Protection Profile (SKPP) promulgated by the Information Assurance Directorate of the U.S. National Security Agency (NSA), and enterprises may seek evaluation and approval of products through the National Information Assurance Partnership (NIAP). Examples of approved, commercially available separation kernels include INTEGRITY-178B from Green Hills Software and VxWorks MILS from Wind River. It should be noted that embedded hypervisors and similar resources found in many multicore processor designs may support implementation of separation kernels, but typically do not, taken alone, meet the requirements for a separation kernel.
- each processor 201 a - 201 h is a separate domain (domain 0 through domain 7).
- Each processor 201 a - 201 h executes a separation kernel to enforce static MMU and PAMU mappings in the MMUs 206 a - 206 h and PAMUs.
- PAMUs 214 - 215 effectively become logically separate PAMUs 214 a - 214 d and 215 a - 215 d for each (for example) 1 Gigabyte Ethernet (“GigE”) communication resource coupled via the coherency fabric 207 .
- GigE Gigabyte Ethernet
- the shared main memory 301 of the system 100 is partitioned by the separation kernel into command, control and status registers 302 , a hardware virtualization private memory 303 , and separate private memories 310 through 317 for each of the separate domains. Because the L3 caches have been disabled and are unused, data co-mingling at that cache level no longer poses a security risk, at a performance penalty that is acceptable for the improved security.
- FIG. 4 diagrammatically illustrates another core isolation and partitioning configuration of a multicore processor with a shared cache that may be realized with a separation kernel to implement a multi-level, hardware-enforced domain separation in accordance with embodiments of the present disclosure.
- the configuration 400 employs all processors 201 a - 201 h of the exemplary multi-core processor of FIG. 2 , together with the respective HV MMUs 206 a - 206 h and PAMUs 214 - 215 .
- each of the processors 201 a - 201 h executes a separation kernel and the L3caches 208 - 209 are enabled.
- the processors 201 a - 201 h are divided into two separate domains (domain 0 and domain 1), with each domain using a separate L3cache.
- each processor 201 a - 201 h executes a separation kernel to enforce static MMU and PAMU mappings in the MMUs 206 a - 206 h and PAMUs 214 a - 214 d and 215 a - 215 d.
- the shared main memory 401 of the system 100 is partitioned by the separation kernel, as above, into command, control and status registers 402 , and a hardware virtualization private memory 403 .
- one L3 cache 208 is used exclusively by one set of processors ( 201 a - 201 d, in the example depicted), while a separate L3 cache 209 is used exclusively for the remaining processors ( 201 e - 201 h, in this example).
- the processors 201 a - 201 h need not be divided equally between the two domains, and the sizes of domain private memories 410 - 411 need not be equal, as in the example depicted and described. Because the L3 caches are each only used within one domain, the security risk of data co-mingling at the L3 cache level can be controlled by assigning either only one application or only trusted applications to execute within one domain, while all other applications execute in the other domain.
- FIGS. 5 and 6 are high level flowcharts for processes of configuring core isolation and partitioning in a multicore processor with a shared cache executing a separation kernel to implement a multi-level, hardware-enforced domain separation in accordance with embodiments of the present disclosure.
- the process 500 illustrated by FIG. 5 begins with performance of the boot process for a separation kernel within a multicore processor (step 501 ).
- the boot process for a multicore processor begins with booting one of the cores, core 0 in this example, to a point of functionality allowing that core to set certain configuration parameters for the entire multicore processor (i.e., enforced on all cores).
- any shared caches within the memory hierarchy are disabled (step 503 ). In the example of FIG. 2 , both shared L3 caches 208 - 209 are disabled.
- caches at other levels may be additional caches at other levels (e.g., below L3) between the processors and shared system memory that are shared, or caches at other levels that are shared between processors (e.g., a shared L2 cache).
- Shared caches are disabled, but private caches (such as caches 203 - 205 in the example of FIG. 2 ) remain enabled and are utilized together with shared system memory. With shared caches disabled, security attacks based on data co-mingling within such caches are precluded.
- the enforcement of static MMU and PAMU virtual address mappings by the separation kernel creates isolated domains (one for each core, in this example), minimizing opportunities for security attacks based on data co-mingling.
- the process 600 illustrated by FIG. 6 also begins with performance of the boot process for a separation kernel within a multicore processor (step 601 ).
- the enforcement of static MMU and PAMU virtual address mappings by the separation kernel is performed by taking into consideration the architecture of the shared cache(s) and the cores, so that only selected processors access a particular shared cache. For an architecture with two shared caches at a given level, half of the cores may be restricted to using one of the shared caches and the remaining cores to using the other, as in the example described above. Alternatively, as few as one core may be permitted to use one cache by the enforced static MMU and PAMU mappings, with the remaining cores allowed only to use other cache(s).
- This effective extension of the separation kernel's private memory domains from system memory up into the shared caches creates at least two isolated domains.
- the domain of a selected security-sensitive application is restricted (step 603 ) to the exclusion of other applications that are either untrusted or for which data co-mingling is deemed a security risk not worth the available performance gains, opportunities for security attacks based on data co-mingling are minimized.
- FIGS. 5 and 6 are not actually mutually exclusive with respect to use or non-use of available shared caches.
- use of shared caches may be selectively disabled for certain processing cores while static MMU/PAMU mappings are enforced to both isolate domains within shared system memory and extend such isolation to nominally shared caches.
- use of a shared cache may be disabled for all but one core, which executes only the security and latency sensitive application (all other applications restricted to other cores).
- a multicore processor having hardware security enforcement may be employed to implement an efficient embedded MLS system by executing a separation kernel on the processing cores and organizing the processing cores to take advantage of the available hardware enforcement technologies.
- the selective disabling of shared caches and/or extension of domain isolation imposed by the separation kernel from shared system memory up into any shared (and enabled) caches reduces security risks from data co-mingling.
- MLS multi-level secure
- AMP symmetric multi-processor
- SoC Freescale QorIQ system-on-a-chip
- SoC Freescale QorIQ system-on-a-chip
- QorIQ Trust Architecture together with an approved separation kernel, co-mingling of data for different security level processing can be prevented.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Human Computer Interaction (AREA)
- Computer Security & Cryptography (AREA)
- Memory System Of A Hierarchy Structure (AREA)
Abstract
Description
- The present disclosure is directed in general to multicore processor systems, and, more particularly, to multicore processor systems with at least one shared cache.
- Multicore processors include multiple processing cores on the same integrated circuit die, usually with private, high-level caches also on the same die and often with a shared, lower-level cache either on the same die or in the same package. These configurations have made possible previously theoretical but impractical security attacks, such as timed thread switching and page table entry modification.
- There is, therefore, a need in the art for improved data security in multicore processor systems.
- A separation kernel isolating memory domains within a shared system memory is executed on the cores of a multicore processor having hardware security enforcement for static virtual address mappings, to implement an efficient embedded multi-level security system. Shared caches are either disabled or constrained by the same static virtual address mappings using the hardware security enforcement available, to isolate domains accessible to select cores and reduce security risks from data co-mingling.
- Although specific advantages have been enumerated above, various embodiments may include some, none, or all of the enumerated advantages. Additionally, other technical advantages may become readily apparent to one of ordinary skill in the art after review of the following figures and description.
- For a more complete understanding of the present disclosure and its advantages, reference is now made to the following description taken in conjunction with the accompanying drawings, in which like reference numerals represent like parts:
-
FIG. 1 is a high level block diagram of a system implementing multi-level, hardware-enforced domain separation using a separation kernel on a multicore processor with a shared cache in accordance with embodiments of the present disclosure; -
FIG. 2 is a high level block diagram of a multicore processor with a shared cache that may be employed to implement multi-level, hardware-enforced domain separation using a separation kernel in accordance with embodiments of the present disclosure; -
FIG. 3 diagrammatically illustrates one core isolation and partitioning configuration of a multicore processor with a shared cache that may be realized with a separation kernel to implement a multi-level, hardware-enforced domain separation in accordance with embodiments of the present disclosure; -
FIG. 4 diagrammatically illustrates another core isolation and partitioning configuration of a multicore processor with a shared cache that may be realized with a separation kernel to implement a multi-level, hardware-enforced domain separation in accordance with embodiments of the present disclosure; and -
FIGS. 5 and 6 are high level flowcharts for processes of configuring core isolation and partitioning in a multicore processor with a shared cache executing a separation kernel to implement a multi-level, hardware-enforced domain separation in accordance with embodiments of the present disclosure. - It should be understood at the outset that, although exemplary embodiments are illustrated in the figures and described below, the principles of the present disclosure may be implemented using any number of techniques, whether currently known or not. The present disclosure should in no way be limited to the exemplary implementations and techniques illustrated in the drawings and described below. Additionally, unless otherwise specifically noted, articles depicted in the drawings are not necessarily drawn to scale.
- Using an evaluated and approved separation kernel with hardware enforcement as foundation technologies in accordance with the present disclosure, several multi-level secure (MLS) environments running a multicore processor running in asymmetric multi-processing (AMP) mode enable an embedded multicore computer system to support at least two security domains. Based on a Freescale QorIQ system-on-a-chip (SoC) and the built-in QorIQ Trust Architecture, together with an approved separation kernel, co-mingling of data for different security level processing can be prevented. Accordingly, by organizing the processing cores to take advantage of available hardware enforcement technologies, an efficient embedded MLS system may be implemented on a multicore processor system.
-
FIG. 1 is a high level block diagram of a system implementing multi-level, hardware-enforced domain separation using a separation kernel on a multicore processor with a shared cache in accordance with embodiments of the present disclosure. Thesystem 100 includes amulticore processor 101, which in the exemplary embodiment is one of the QorIQ family of multicore processors available from Freescale Semiconductor, Inc., such as the model P4080 processor. Themulticore processor 101 is communicably coupled by asystem bus 102 to asystem memory 103, and, in the exemplary embodiment, also to atransceiver 104 and to a plurality ofperipheral devices system 100 is not depicted by the drawings or described herein. Instead, for simplicity and clarity, only so much of thesystem 100 as is either unique to the present disclosure or necessary for an understanding of the present disclosure is depicted and described. -
FIG. 2 is a high level block diagram of a multicore processor with a shared cache that may be employed to implement multi-level, hardware-enforced domain separation using a separation kernel in accordance with embodiments of the present disclosure. As noted above, themulticore processor 101 is preferably a Freescale QorIQ processor, although any multiprocessor with the security features described herein may be employed instead. Multicoreprocessor 101 includes a plurality of processors. In the exemplary embodiment, eight processors 201 a-201 h, named “core 0” to “core 7,” are formed in the integrated circuit ofmulticore processor 101. Each processor 201 a-201 h includes aprocessing core 202, the circuitry executing instructions of a program. Each processor also includes a level one (L1) data cache (“D-Cache”) 203 and an L1 instruction cache (“I-Cache”) 204, each 32 kilobytes (KB) in size and each holding working copies of data and program instructions, respectively, for operations executed within therespective processor 202. Eachprocessor 202 also includes a level two (L2) backside cache 205 (e.g., 128 KB), a combined data and instruction cache. - One of the hardware enforcement mechanisms within the
multicore processor 101 of the exemplary embodiment is a memory management unit (MMU), which in the exemplary embodiment is implemented by a hardware virtualization memory management unit (HV MMU) 206. The HV MMU 206 performs, in hardware, virtualization of memory addresses for locations within system memory. That is, ranges of virtual memory addresses defined for use by software operating within theprocessor 201 a (or 201 b, 201 c, etc.) map to physical memory locations. The mapping and subsequent address translations are controlled by HV MMU 206, which is employed at least during read or write accesses to system memory and which operates cooperatively for cache control and, to the extent necessary, bus arbitration. - The two
L1 caches coherency fabric 207, which in the example of a QorIQ processor is implemented by the CoreNet coherency fabric. Front side level three (L3)caches 208 and 209 (e.g., 1024 KB) are also communicably coupled tocoherency fabric 207, and are each coupled to arespective memory controller L3 caches - The
coherency fabric 207 manages coherency of thecaches caches coherency fabric 207 also provides scalable on-chip, point-to-point connectivity supporting concurrent traffic to and from multiple resources connected to thefabric 207, eliminating single-point bottlenecks for non-competing resources and thus avoiding various bus contention and latency issues associated with scaling shared bus/shared memory architectures. Thecoherency fabric 207 is connected with communications resources (not shown), such as Ethernet frame managers/buffers and input/output (I/O) ports according to various other communications standards with test/debug interfaces (also not shown), and/or with security engines and managers (also not shown). Again, those skilled in the art will recognize that the full structure and operation of themulticore processor 101 is not depicted by the drawings or described herein. Instead, for simplicity and clarity, only so much of themulticore processor 101 as is either unique to the present disclosure or necessary for an understanding of the present disclosure is depicted and described. - Another hardware enforcement mechanism within the
multicore processor 101 of the exemplary embodiment is the peripheral access management units (PAMUs) 212, 213, 214, 215 and 216 within thecoherency fabric 207. The PAMUs 212-216 serve as the input/output (I/O) MMUs for themulticore processor 101, providing I/O device-to-memory access control, protection and address translation in a manner allowing creation of a securely partitioned system. While the PAMUs 212-216 may grant direct memory access (DMA) to peripherals, themulticore processor 101 may be configured so that all DMA-capable I/O devices must go through one of the PAMUs for memory accesses, with the respective PAMU employing a set of software-configured tables to determine what physical address ranges the device is permitted to access. -
FIG. 3 diagrammatically illustrates one core isolation and partitioning configuration of a multicore processor with a shared cache that may be realized with a separation kernel to implement a multi-level, hardware-enforced domain separation in accordance with embodiments of the present disclosure. Theconfiguration 300 employs all processors 201 a-201 h of the exemplary multi-core processor ofFIG. 2 , together with therespective HV MMUs 206 a-206 h and PAMUs 214-215. In thisconfiguration 300, each of the processors 201 a-201 h executes a separation kernel and the L3 caches 208-209 are disabled (not utilized). A “separation kernel” is an operating system security kernel used to create an environment that is indistinguishable from physically distributed systems; that is, each domain appears to all other domains as a separate, isolated machine and information flow between domains is limited to known, external communication lines. The characteristics of a separation kernel are defined, for example, by the Separation Kernel Protection Profile (SKPP) promulgated by the Information Assurance Directorate of the U.S. National Security Agency (NSA), and enterprises may seek evaluation and approval of products through the National Information Assurance Partnership (NIAP). Examples of approved, commercially available separation kernels include INTEGRITY-178B from Green Hills Software and VxWorks MILS from Wind River. It should be noted that embedded hypervisors and similar resources found in many multicore processor designs may support implementation of separation kernels, but typically do not, taken alone, meet the requirements for a separation kernel. - In the embodiment of
FIG. 3 , each processor 201 a-201 h is a separate domain (domain 0 through domain 7). Each processor 201 a-201 h executes a separation kernel to enforce static MMU and PAMU mappings in theMMUs 206 a-206 h and PAMUs. As a result, PAMUs 214-215 effectively become logicallyseparate PAMUs 214 a-214 d and 215 a-215 d for each (for example) 1 Gigabyte Ethernet (“GigE”) communication resource coupled via thecoherency fabric 207. In addition, the sharedmain memory 301 of thesystem 100 is partitioned by the separation kernel into command, control and status registers 302, a hardware virtualizationprivate memory 303, and separateprivate memories 310 through 317 for each of the separate domains. Because the L3 caches have been disabled and are unused, data co-mingling at that cache level no longer poses a security risk, at a performance penalty that is acceptable for the improved security. -
FIG. 4 diagrammatically illustrates another core isolation and partitioning configuration of a multicore processor with a shared cache that may be realized with a separation kernel to implement a multi-level, hardware-enforced domain separation in accordance with embodiments of the present disclosure. Theconfiguration 400 employs all processors 201 a-201 h of the exemplary multi-core processor ofFIG. 2 , together with therespective HV MMUs 206 a-206 h and PAMUs 214-215. In thisconfiguration 400, each of the processors 201 a-201 h executes a separation kernel and the L3caches 208-209 are enabled. In this embodiment, however, the processors 201 a-201 h are divided into two separate domains (domain 0 and domain 1), with each domain using a separate L3cache. As above, each processor 201 a-201 h executes a separation kernel to enforce static MMU and PAMU mappings in theMMUs 206 a-206 h andPAMUs 214 a-214 d and 215 a-215 d. In addition, the sharedmain memory 401 of thesystem 100 is partitioned by the separation kernel, as above, into command, control and status registers 402, and a hardware virtualization private memory 403. On the other hand, only two partitions are necessary as separateprivate memories L3 cache 208 is used exclusively by one set of processors (201 a-201 d, in the example depicted), while aseparate L3 cache 209 is used exclusively for the remaining processors (201 e-201 h, in this example). Of course, the processors 201 a-201 h need not be divided equally between the two domains, and the sizes of domain private memories 410-411 need not be equal, as in the example depicted and described. Because the L3 caches are each only used within one domain, the security risk of data co-mingling at the L3 cache level can be controlled by assigning either only one application or only trusted applications to execute within one domain, while all other applications execute in the other domain. -
FIGS. 5 and 6 are high level flowcharts for processes of configuring core isolation and partitioning in a multicore processor with a shared cache executing a separation kernel to implement a multi-level, hardware-enforced domain separation in accordance with embodiments of the present disclosure. While each process flow and/or event sequence depicted in the figures and described involves a sequence of steps and/or events, occurring either in series or in tandem, unless explicitly stated or otherwise self-evident (e.g., a signal cannot be received before being transmitted), no inference should be drawn regarding specific order of performance of steps or occurrence of events, performance of steps or portions thereof or occurrence of events serially rather than concurrently or in an overlapping manner, or performance the steps or occurrence of the events depicted exclusively without the occurrence of intervening or intermediate steps or events. Moreover, those skilled in the art will recognize that complete processes and event sequences are not illustrated or described. Instead, for simplicity and clarity, only so much of the respective processes and event sequences as is unique to the present disclosure or necessary for an understanding of the present disclosure is depicted and described. - The
process 500 illustrated byFIG. 5 begins with performance of the boot process for a separation kernel within a multicore processor (step 501). Typically the boot process for a multicore processor begins with booting one of the cores,core 0 in this example, to a point of functionality allowing that core to set certain configuration parameters for the entire multicore processor (i.e., enforced on all cores). Accordingly, once the primary core has been sufficiently booted (step 502), any shared caches within the memory hierarchy are disabled (step 503). In the example ofFIG. 2 , both shared L3 caches 208-209 are disabled. In other embodiments, however, there may be additional caches at other levels (e.g., below L3) between the processors and shared system memory that are shared, or caches at other levels that are shared between processors (e.g., a shared L2 cache). Shared caches are disabled, but private caches (such as caches 203-205 in the example ofFIG. 2 ) remain enabled and are utilized together with shared system memory. With shared caches disabled, security attacks based on data co-mingling within such caches are precluded. Within the shared system memory, the enforcement of static MMU and PAMU virtual address mappings by the separation kernel (step 504) creates isolated domains (one for each core, in this example), minimizing opportunities for security attacks based on data co-mingling. - The
process 600 illustrated byFIG. 6 also begins with performance of the boot process for a separation kernel within a multicore processor (step 601). Rather than disabling shared caches, however, the enforcement of static MMU and PAMU virtual address mappings by the separation kernel (step 602) is performed by taking into consideration the architecture of the shared cache(s) and the cores, so that only selected processors access a particular shared cache. For an architecture with two shared caches at a given level, half of the cores may be restricted to using one of the shared caches and the remaining cores to using the other, as in the example described above. Alternatively, as few as one core may be permitted to use one cache by the enforced static MMU and PAMU mappings, with the remaining cores allowed only to use other cache(s). This effective extension of the separation kernel's private memory domains from system memory up into the shared caches creates at least two isolated domains. When the domain of a selected security-sensitive application is restricted (step 603), to the exclusion of other applications that are either untrusted or for which data co-mingling is deemed a security risk not worth the available performance gains, opportunities for security attacks based on data co-mingling are minimized. - It will be noted by those skilled in the art that the techniques of
FIGS. 5 and 6 are not actually mutually exclusive with respect to use or non-use of available shared caches. For architectures in which use of a shared cache may be enabled or disabled on a core-by-core basis, for example, use of shared caches may be selectively disabled for certain processing cores while static MMU/PAMU mappings are enforced to both isolate domains within shared system memory and extend such isolation to nominally shared caches. For a system executing one security and latency sensitive application and a plurality of applications for which the latency without caching is acceptable, use of a shared cache may be disabled for all but one core, which executes only the security and latency sensitive application (all other applications restricted to other cores). - A multicore processor having hardware security enforcement may be employed to implement an efficient embedded MLS system by executing a separation kernel on the processing cores and organizing the processing cores to take advantage of the available hardware enforcement technologies. In particular, the selective disabling of shared caches and/or extension of domain isolation imposed by the separation kernel from shared system memory up into any shared (and enabled) caches reduces security risks from data co-mingling.
- Using an evaluated and approved separation kernel with hardware enforcement as foundation technologies in accordance with the present disclosure, several multi-level secure (MLS) environments running a multicore processor running in asymmetric multi-processor (AMP) mode enable an embedded multicore computer system to support at least two security domains. Based on a Freescale QorIQ system-on-a-chip (SoC) and the built-in QorIQ Trust Architecture, together with an approved separation kernel, co-mingling of data for different security level processing can be prevented.
- Modifications, additions, or omissions may be made to the systems, apparatuses, and methods described herein without departing from the scope of the disclosure. For example, the components of the systems and apparatuses may be integrated or separated. Moreover, the operations of the systems and apparatuses disclosed herein may be performed by more, fewer, or other components and the methods described may include more, fewer, or other steps. Additionally, steps may be performed in any suitable order. As used in this document, “each” refers to each member of a set or each member of a subset of a set.
- To aid the Patent Office and any readers of any patent issued on this application in interpreting the claims appended hereto, applicants wish to note that they do not intend any of the appended claims or claim elements to invoke 35 U.S.C. §112(f) unless the words “means for” or “step for” are explicitly used in the particular claim.
Claims (20)
Priority Applications (6)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US14/480,456 US9436619B2 (en) | 2014-09-08 | 2014-09-08 | Multi-level, hardware-enforced domain separation using a separation kernel on a multicore processor with a shared cache |
AU2015315801A AU2015315801B2 (en) | 2014-09-08 | 2015-07-07 | Multi-level, hardware-enforced domain separation using a separation kernel on a multicore processor with a shared cache |
EP15739453.7A EP3191966B1 (en) | 2014-09-08 | 2015-07-07 | Multi-level, hardware-enforced domain separation using a separation kernel on a multicore processor with a shared cache |
PCT/US2015/039394 WO2016039841A1 (en) | 2014-09-08 | 2015-07-07 | Multi-level, hardware-enforced domain separation using a separation kernel on a multicore processor with a shared cache |
EP19190794.8A EP3598309B1 (en) | 2014-09-08 | 2015-07-07 | Multi-level, hardware-enforced domain separation using a separation kernel on a multicore processor with a shared cache |
IL250714A IL250714B (en) | 2014-09-08 | 2017-02-22 | Multi-level, hardware-enforced domain separation using a separation kernel on a multicore processor with a shared cache |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US14/480,456 US9436619B2 (en) | 2014-09-08 | 2014-09-08 | Multi-level, hardware-enforced domain separation using a separation kernel on a multicore processor with a shared cache |
Publications (2)
Publication Number | Publication Date |
---|---|
US20160070658A1 true US20160070658A1 (en) | 2016-03-10 |
US9436619B2 US9436619B2 (en) | 2016-09-06 |
Family
ID=53682861
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US14/480,456 Active 2034-11-13 US9436619B2 (en) | 2014-09-08 | 2014-09-08 | Multi-level, hardware-enforced domain separation using a separation kernel on a multicore processor with a shared cache |
Country Status (5)
Country | Link |
---|---|
US (1) | US9436619B2 (en) |
EP (2) | EP3191966B1 (en) |
AU (1) | AU2015315801B2 (en) |
IL (1) | IL250714B (en) |
WO (1) | WO2016039841A1 (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108154054A (en) * | 2016-12-02 | 2018-06-12 | Arm 有限公司 | Filter coherency protocol transaction |
US10198373B2 (en) * | 2016-11-30 | 2019-02-05 | International Business Machines Corporation | Uniform memory access architecture |
CN110210214A (en) * | 2019-06-03 | 2019-09-06 | 成都海光集成电路设计有限公司 | Processor core partition method and device |
US20200285595A1 (en) * | 2019-03-08 | 2020-09-10 | International Business Machines Corporation | Secure storage isolation |
US20210073042A1 (en) * | 2019-09-05 | 2021-03-11 | Nvidia Corporation | Techniques for configuring a processor to function as multiple, separate processors |
US20210224392A1 (en) * | 2020-01-21 | 2021-07-22 | Wind River Systems, Inc. | Tri-Level Secure Separation Kernel |
US11663036B2 (en) | 2019-09-05 | 2023-05-30 | Nvidia Corporation | Techniques for configuring a processor to function as multiple, separate processors |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10846117B1 (en) * | 2015-12-10 | 2020-11-24 | Fireeye, Inc. | Technique for establishing secure communication between host and guest processes of a virtualization architecture |
US10447728B1 (en) | 2015-12-10 | 2019-10-15 | Fireeye, Inc. | Technique for protecting guest processes using a layered virtualization architecture |
US10108446B1 (en) | 2015-12-11 | 2018-10-23 | Fireeye, Inc. | Late load technique for deploying a virtualization layer underneath a running operating system |
US11899585B2 (en) * | 2021-12-24 | 2024-02-13 | Western Digital Technologies, Inc. | In-kernel caching for distributed cache |
US11934663B2 (en) | 2022-01-10 | 2024-03-19 | Western Digital Technologies, Inc. | Computational acceleration for distributed cache |
US11797379B2 (en) | 2022-02-04 | 2023-10-24 | Western Digital Technologies, Inc. | Error detection and data recovery for distributed cache |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6754776B2 (en) * | 2001-05-17 | 2004-06-22 | Fujitsu Limited | Method and system for logical partitioning of cache memory structures in a partitoned computer system |
US7130977B1 (en) | 2002-04-18 | 2006-10-31 | Advanced Micro Devices, Inc. | Controlling access to a control register of a microprocessor |
US8190839B2 (en) | 2009-03-11 | 2012-05-29 | Applied Micro Circuits Corporation | Using domains for physical address management in a multiprocessor system |
US8549249B1 (en) | 2009-09-21 | 2013-10-01 | Tilera Corporation | Supporting secondary atomic operations using primary atomic operations |
WO2011161774A1 (en) * | 2010-06-22 | 2011-12-29 | 富士通株式会社 | Multi-core processor system, control program, and control method |
US10514938B2 (en) | 2012-12-18 | 2019-12-24 | Dynavisor, Inc. | Making direct calls to a native device driver of a hypervisor using dynamic device driver virtualization |
-
2014
- 2014-09-08 US US14/480,456 patent/US9436619B2/en active Active
-
2015
- 2015-07-07 EP EP15739453.7A patent/EP3191966B1/en active Active
- 2015-07-07 AU AU2015315801A patent/AU2015315801B2/en active Active
- 2015-07-07 EP EP19190794.8A patent/EP3598309B1/en active Active
- 2015-07-07 WO PCT/US2015/039394 patent/WO2016039841A1/en active Application Filing
-
2017
- 2017-02-22 IL IL250714A patent/IL250714B/en active IP Right Grant
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10198373B2 (en) * | 2016-11-30 | 2019-02-05 | International Business Machines Corporation | Uniform memory access architecture |
US10599590B2 (en) | 2016-11-30 | 2020-03-24 | International Business Machines Corporation | Uniform memory access architecture |
CN108154054A (en) * | 2016-12-02 | 2018-06-12 | Arm 有限公司 | Filter coherency protocol transaction |
US10664399B2 (en) * | 2016-12-02 | 2020-05-26 | Arm Limited | Filtering coherency protocol transactions |
US20200285595A1 (en) * | 2019-03-08 | 2020-09-10 | International Business Machines Corporation | Secure storage isolation |
US11531627B2 (en) * | 2019-03-08 | 2022-12-20 | International Business Machines Corporation | Secure storage isolation |
CN110210214A (en) * | 2019-06-03 | 2019-09-06 | 成都海光集成电路设计有限公司 | Processor core partition method and device |
US20210073042A1 (en) * | 2019-09-05 | 2021-03-11 | Nvidia Corporation | Techniques for configuring a processor to function as multiple, separate processors |
US11663036B2 (en) | 2019-09-05 | 2023-05-30 | Nvidia Corporation | Techniques for configuring a processor to function as multiple, separate processors |
US11893423B2 (en) * | 2019-09-05 | 2024-02-06 | Nvidia Corporation | Techniques for configuring a processor to function as multiple, separate processors |
US20210224392A1 (en) * | 2020-01-21 | 2021-07-22 | Wind River Systems, Inc. | Tri-Level Secure Separation Kernel |
US11748484B2 (en) * | 2020-01-21 | 2023-09-05 | Wind River Systems, Inc. | Tri-level secure separation kernel |
Also Published As
Publication number | Publication date |
---|---|
IL250714B (en) | 2019-12-31 |
US9436619B2 (en) | 2016-09-06 |
EP3598309B1 (en) | 2022-05-11 |
AU2015315801A1 (en) | 2017-03-02 |
EP3191966A1 (en) | 2017-07-19 |
EP3191966B1 (en) | 2019-10-23 |
AU2015315801B2 (en) | 2020-05-21 |
EP3598309A1 (en) | 2020-01-22 |
WO2016039841A1 (en) | 2016-03-17 |
IL250714A0 (en) | 2017-04-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9436619B2 (en) | Multi-level, hardware-enforced domain separation using a separation kernel on a multicore processor with a shared cache | |
US10901772B2 (en) | Virtualization exceptions | |
US8893267B1 (en) | System and method for partitioning resources in a system-on-chip (SoC) | |
US9519596B2 (en) | Resource access control in a system-on-chip | |
EP3185128B1 (en) | Gpu virtualisation | |
KR101861297B1 (en) | Efficient memory and resource management | |
US8631212B2 (en) | Input/output memory management unit with protection mode for preventing memory access by I/O devices | |
US9858202B2 (en) | Low overhead paged memory runtime protection | |
Porquet et al. | NoC-MPU: A secure architecture for flexible co-hosting on shared memory MPSoCs | |
US10257166B2 (en) | Guest netfilter protection by virtual machine function | |
US10402576B2 (en) | Safe physical function passthrough using virtual machine functions | |
US10552345B2 (en) | Virtual machine memory lock-down | |
US20160188354A1 (en) | Efficient enabling of extended page tables | |
US10671419B2 (en) | Multiple input-output memory management units with fine grained device scopes for virtual machines | |
US20190227834A1 (en) | Application memory protection using an extended page table switching virtual machine function | |
US10698713B2 (en) | Virtual processor state switching virtual machine functions | |
US9086906B2 (en) | Apparatus and method for guest and root register sharing in a virtual machine | |
US10956571B2 (en) | Kernel runtime integrity using processor assists | |
Dévigne et al. | Executing secured virtual machines within a manycore architecture | |
Kornaros et al. | Towards full virtualization of heterogeneous noc-based multicore embedded architectures | |
Kegel et al. | Virtualizing io through io memory management unit (iommu) |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: RAYTHEON COMPANY, MASSACHUSETTS Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:WOOLLEY, BRANDON;REEL/FRAME:033693/0386 Effective date: 20140902 |
|
FEPP | Fee payment procedure |
Free format text: PAYOR NUMBER ASSIGNED (ORIGINAL EVENT CODE: ASPN); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY |
|
STCF | Information on status: patent grant |
Free format text: PATENTED CASE |
|
MAFP | Maintenance fee payment |
Free format text: PAYMENT OF MAINTENANCE FEE, 4TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1551); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY Year of fee payment: 4 |
|
MAFP | Maintenance fee payment |
Free format text: PAYMENT OF MAINTENANCE FEE, 8TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1552); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY Year of fee payment: 8 |